Files
ScadaBridge/src/ScadaLink.Transport/Import/BundleImporter.cs
T
2026-05-24 04:41:24 -04:00

435 lines
20 KiB
C#
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
using System.Security.Cryptography;
using System.Text.Json;
using System.Text.Json.Serialization;
using Microsoft.Extensions.Options;
using ScadaLink.Commons.Entities.Templates;
using ScadaLink.Commons.Interfaces.Repositories;
using ScadaLink.Commons.Interfaces.Services;
using ScadaLink.Commons.Interfaces.Transport;
using ScadaLink.Commons.Types.Transport;
using ScadaLink.ConfigurationDatabase;
using ScadaLink.Transport.Encryption;
using ScadaLink.Transport.Serialization;
namespace ScadaLink.Transport.Import;
/// <summary>
/// Three-phase bundle importer: <see cref="LoadAsync"/> validates the
/// bundle envelope (manifest + content hash + decryption) and opens a
/// session; <see cref="PreviewAsync"/> diffs the bundle's DTOs against the
/// current target database; <see cref="ApplyAsync"/> writes the chosen
/// resolutions through the audited repositories. Only LoadAsync is
/// implemented in this slice — the other two are wired into DI now so
/// follow-up tasks can fill them in without churning the constructor.
/// </summary>
public sealed class BundleImporter : IBundleImporter
{
private static readonly JsonSerializerOptions ContentJsonOptions = new()
{
WriteIndented = false,
DefaultIgnoreCondition = JsonIgnoreCondition.WhenWritingNull,
Converters = { new JsonStringEnumConverter() },
};
private readonly BundleSerializer _bundleSerializer;
private readonly ManifestValidator _manifestValidator;
private readonly BundleSecretEncryptor _encryptor;
private readonly ArtifactDiff _diff = new();
#pragma warning disable IDE0052 // wired-in dependencies for T17.
private readonly EntitySerializer _entitySerializer;
private readonly IAuditService _auditService;
private readonly IAuditCorrelationContext _correlationContext;
private readonly ScadaLinkDbContext _dbContext;
#pragma warning restore IDE0052
private readonly ITemplateEngineRepository _templateRepo;
private readonly IExternalSystemRepository _externalRepo;
private readonly INotificationRepository _notificationRepo;
private readonly IInboundApiRepository _inboundApiRepo;
private readonly IBundleSessionStore _sessionStore;
private readonly IOptions<TransportOptions> _options;
private readonly TimeProvider _timeProvider;
public BundleImporter(
BundleSerializer bundleSerializer,
ManifestValidator manifestValidator,
BundleSecretEncryptor encryptor,
EntitySerializer entitySerializer,
IBundleSessionStore sessionStore,
IOptions<TransportOptions> options,
TimeProvider timeProvider,
ITemplateEngineRepository templateRepo,
IExternalSystemRepository externalRepo,
INotificationRepository notificationRepo,
IInboundApiRepository inboundApiRepo,
IAuditService auditService,
IAuditCorrelationContext correlationContext,
ScadaLinkDbContext dbContext)
{
_bundleSerializer = bundleSerializer ?? throw new ArgumentNullException(nameof(bundleSerializer));
_manifestValidator = manifestValidator ?? throw new ArgumentNullException(nameof(manifestValidator));
_encryptor = encryptor ?? throw new ArgumentNullException(nameof(encryptor));
_entitySerializer = entitySerializer ?? throw new ArgumentNullException(nameof(entitySerializer));
_sessionStore = sessionStore ?? throw new ArgumentNullException(nameof(sessionStore));
_options = options ?? throw new ArgumentNullException(nameof(options));
_timeProvider = timeProvider ?? throw new ArgumentNullException(nameof(timeProvider));
_templateRepo = templateRepo ?? throw new ArgumentNullException(nameof(templateRepo));
_externalRepo = externalRepo ?? throw new ArgumentNullException(nameof(externalRepo));
_notificationRepo = notificationRepo ?? throw new ArgumentNullException(nameof(notificationRepo));
_inboundApiRepo = inboundApiRepo ?? throw new ArgumentNullException(nameof(inboundApiRepo));
_auditService = auditService ?? throw new ArgumentNullException(nameof(auditService));
_correlationContext = correlationContext ?? throw new ArgumentNullException(nameof(correlationContext));
_dbContext = dbContext ?? throw new ArgumentNullException(nameof(dbContext));
}
/// <summary>
/// Validates the bundle envelope and opens a session keyed by a fresh GUID.
/// Wrong-passphrase failures surface as <see cref="CryptographicException"/>
/// so the caller (UI / API endpoint) can increment the lockout counter on
/// the returned session — this method does not mutate <c>FailedUnlockAttempts</c>
/// itself because the session does not exist yet at the point of failure.
/// </summary>
public async Task<BundleSession> LoadAsync(Stream bundleStream, string? passphrase, CancellationToken ct = default)
{
ArgumentNullException.ThrowIfNull(bundleStream);
// Copy to a seekable buffer — manifest + content readers each open a
// fresh ZipArchive over the same bytes, so the upstream stream needs to
// be seekable. A caller-supplied FileStream is seekable but a Kestrel
// request stream is not, so we always normalise to MemoryStream.
var ms = new MemoryStream();
await bundleStream.CopyToAsync(ms, ct).ConfigureAwait(false);
ms.Position = 0;
// Size cap is in MB; multiply in long arithmetic so the comparison
// doesn't overflow at the int boundary for large MaxBundleSizeMb.
var maxBytes = _options.Value.MaxBundleSizeMb * 1024L * 1024L;
if (ms.Length > maxBytes)
{
throw new InvalidOperationException(
$"Bundle exceeds maximum allowed size of {_options.Value.MaxBundleSizeMb} MB.");
}
BundleManifest manifest;
try
{
ms.Position = 0;
manifest = _bundleSerializer.ReadManifest(ms);
}
catch (InvalidDataException)
{
// Preserve the serializer's specific "manifest missing/null" message
// — the caller wants to surface a precise diagnostic to the operator.
throw;
}
catch (Exception ex)
{
throw new InvalidDataException("Bundle is missing or has a malformed manifest.json.", ex);
}
ms.Position = 0;
var contentBytes = _bundleSerializer.ReadContentBytes(ms, manifest);
// Validate format version + content-hash + manifest shape. Reject paths
// surface as distinct exceptions so the UI can disambiguate the cause.
var validation = _manifestValidator.Validate(manifest, contentBytes);
switch (validation)
{
case ManifestValidationResult.UnsupportedFormatVersion:
throw new NotSupportedException(
$"Bundle format version {manifest.BundleFormatVersion} is not supported by this cluster.");
case ManifestValidationResult.ContentHashMismatch:
throw new InvalidDataException(
"Bundle content hash does not match manifest — file may be corrupt.");
case ManifestValidationResult.MalformedManifest:
throw new InvalidDataException("Bundle manifest is malformed.");
case ManifestValidationResult.Ok:
break;
default:
throw new InvalidDataException($"Unrecognised manifest validation result: {validation}.");
}
// Decrypt when the manifest carries EncryptionMetadata. AES-GCM tag
// mismatch surfaces as a CryptographicException (or its
// AuthenticationTagMismatchException subclass on .NET 10+) — bubble it
// unchanged so the caller can detect wrong-passphrase via type check
// and increment the lockout counter on the (about-to-be-rejected)
// session reference. The session is not opened on the failure path.
byte[] decryptedContent;
if (manifest.Encryption is not null)
{
if (string.IsNullOrEmpty(passphrase))
{
throw new ArgumentException(
"Passphrase required for encrypted bundle.", nameof(passphrase));
}
decryptedContent = _encryptor.Decrypt(contentBytes, manifest.Encryption, passphrase);
}
else
{
decryptedContent = contentBytes;
}
var ttl = TimeSpan.FromMinutes(_options.Value.BundleSessionTtlMinutes);
var session = new BundleSession
{
SessionId = Guid.NewGuid(),
Manifest = manifest,
DecryptedContent = decryptedContent,
ExpiresAt = _timeProvider.GetUtcNow() + ttl,
};
return _sessionStore.Open(session);
}
/// <summary>
/// Diffs every artifact in the loaded bundle against the current target
/// database. Lookups are name-keyed (the bundle is portable across
/// environments so FK ids never line up). Emits <see cref="ConflictKind.Blocker"/>
/// items when a bundled template references a SharedScript or ExternalSystem
/// that is in neither the bundle nor the target — that import would crash at
/// runtime, so we surface it in the preview UI before Apply.
/// </summary>
public async Task<ImportPreview> PreviewAsync(Guid sessionId, CancellationToken ct = default)
{
var session = _sessionStore.Get(sessionId)
?? throw new InvalidOperationException($"Bundle session {sessionId} not found or expired.");
if (session.Locked)
{
throw new InvalidOperationException($"Bundle session {sessionId} is locked.");
}
BundleContentDto content;
try
{
content = JsonSerializer.Deserialize<BundleContentDto>(session.DecryptedContent, ContentJsonOptions)
?? throw new InvalidDataException("Session content deserialized to null.");
}
catch (JsonException ex)
{
throw new InvalidDataException("Session content is not a valid BundleContentDto.", ex);
}
var items = new List<ImportPreviewItem>();
// ---- TemplateFolders ----
var allFolders = await _templateRepo.GetAllFoldersAsync(ct).ConfigureAwait(false);
var folderByName = allFolders.ToDictionary(f => f.Name, f => f, StringComparer.Ordinal);
var folderNameById = allFolders.ToDictionary(f => f.Id, f => f.Name);
foreach (var fDto in content.TemplateFolders)
{
folderByName.TryGetValue(fDto.Name, out var existing);
items.Add(_diff.CompareTemplateFolder(fDto, existing, folderNameById));
}
// ---- Templates ----
// Repos only expose GetTemplateByIdAsync / GetAllTemplatesAsync — no
// by-name lookup. Pull all once and index by name for the diff loop.
var allTemplates = await _templateRepo.GetAllTemplatesAsync(ct).ConfigureAwait(false);
var hydratedByName = new Dictionary<string, Template>(StringComparer.Ordinal);
foreach (var stub in allTemplates)
{
// GetAllTemplatesAsync may not eager-load children — fetch the
// children-loaded variant for any name that matches an incoming DTO
// so the per-child diff loop sees the full collection.
if (content.Templates.Any(t => string.Equals(t.Name, stub.Name, StringComparison.Ordinal)))
{
var hydrated = await _templateRepo.GetTemplateWithChildrenAsync(stub.Id, ct).ConfigureAwait(false);
if (hydrated is not null)
{
hydratedByName[stub.Name] = hydrated;
}
}
}
foreach (var tDto in content.Templates)
{
hydratedByName.TryGetValue(tDto.Name, out var existing);
items.Add(_diff.CompareTemplate(tDto, existing));
}
// ---- SharedScripts ----
foreach (var s in content.SharedScripts)
{
var existing = await _templateRepo.GetSharedScriptByNameAsync(s.Name, ct).ConfigureAwait(false);
items.Add(_diff.CompareSharedScript(s, existing));
}
// ---- ExternalSystems (+ their methods) ----
foreach (var es in content.ExternalSystems)
{
var existing = await _externalRepo.GetExternalSystemByNameAsync(es.Name, ct).ConfigureAwait(false);
IReadOnlyList<Commons.Entities.ExternalSystems.ExternalSystemMethod>? methods = null;
if (existing is not null)
{
methods = await _externalRepo.GetMethodsByExternalSystemIdAsync(existing.Id, ct).ConfigureAwait(false);
}
items.Add(_diff.CompareExternalSystem(es, existing, methods));
}
// ---- DatabaseConnections ----
foreach (var db in content.DatabaseConnections)
{
var existing = await _externalRepo.GetDatabaseConnectionByNameAsync(db.Name, ct).ConfigureAwait(false);
items.Add(_diff.CompareDatabaseConnection(db, existing));
}
// ---- NotificationLists ----
foreach (var nl in content.NotificationLists)
{
var existing = await _notificationRepo.GetListByNameAsync(nl.Name, ct).ConfigureAwait(false);
items.Add(_diff.CompareNotificationList(nl, existing));
}
// ---- SmtpConfigurations (no by-host lookup — scan GetAll) ----
var allSmtp = await _notificationRepo.GetAllSmtpConfigurationsAsync(ct).ConfigureAwait(false);
var smtpByHost = allSmtp.ToDictionary(s => s.Host, s => s, StringComparer.Ordinal);
foreach (var sm in content.SmtpConfigs)
{
smtpByHost.TryGetValue(sm.Host, out var existing);
items.Add(_diff.CompareSmtpConfiguration(sm, existing));
}
// ---- ApiKeys (no by-name lookup — scan GetAll) ----
var allApiKeys = await _inboundApiRepo.GetAllApiKeysAsync(ct).ConfigureAwait(false);
var apiKeyByName = allApiKeys.ToDictionary(k => k.Name, k => k, StringComparer.Ordinal);
foreach (var k in content.ApiKeys)
{
apiKeyByName.TryGetValue(k.Name, out var existing);
items.Add(_diff.CompareApiKey(k, existing));
}
// ---- ApiMethods ----
foreach (var m in content.ApiMethods)
{
var existing = await _inboundApiRepo.GetMethodByNameAsync(m.Name, ct).ConfigureAwait(false);
items.Add(_diff.CompareApiMethod(m, existing));
}
// ---- Blocker detection ----
items.AddRange(await DetectBlockersAsync(content, ct).ConfigureAwait(false));
return new ImportPreview(sessionId, items);
}
/// <summary>
/// Surfaces unresolved cross-entity references: a TemplateScript or
/// ApiMethod body that name-mentions a SharedScript or ExternalSystem that
/// is in neither the bundle nor the target database. We reuse the same
/// substring-with-word-boundary scan as <c>DependencyResolver</c>; the
/// implementations are kept in lockstep but not factored out yet because
/// the resolver's scan operates on entity Code while the importer's scan
/// operates on DTO Code — same algorithm, different inputs.
/// </summary>
private async Task<IReadOnlyList<ImportPreviewItem>> DetectBlockersAsync(BundleContentDto content, CancellationToken ct)
{
var blockers = new List<ImportPreviewItem>();
// Known-resolvable names = (in-bundle) (already-in-target).
var allSharedScripts = await _templateRepo.GetAllSharedScriptsAsync(ct).ConfigureAwait(false);
var allExternalSystems = await _externalRepo.GetAllExternalSystemsAsync(ct).ConfigureAwait(false);
var sharedScriptNames = new HashSet<string>(StringComparer.Ordinal);
foreach (var s in content.SharedScripts) sharedScriptNames.Add(s.Name);
foreach (var s in allSharedScripts) sharedScriptNames.Add(s.Name);
var externalSystemNames = new HashSet<string>(StringComparer.Ordinal);
foreach (var e in content.ExternalSystems) externalSystemNames.Add(e.Name);
foreach (var e in allExternalSystems) externalSystemNames.Add(e.Name);
// Heuristic: collect a small candidate vocabulary of identifiers used
// by the bundle's scripts that are NOT one of the known-good names, and
// check whether each one was previously a SharedScript or ExternalSystem
// (i.e. matches the naming-convention shape of an identifier reference).
// For v1, we walk the SharedScripts the bundle *expects* — by scanning
// bodies and reporting any identifier-shaped token that resolves to a
// SharedScript by historical record... but that's overreach.
//
// Simpler + sufficient v1: scan every script body in the bundle's
// templates + ApiMethods, and for each occurrence of "Name(" where
// Name is a valid identifier, if Name appears in NEITHER set, surface
// it as a Blocker. This catches the documented use-case
// (HelperFn() / ErpSystem.Call()) without combinatorial blowup.
var referencedFromBundle = new HashSet<string>(StringComparer.Ordinal);
foreach (var t in content.Templates)
{
foreach (var s in t.Scripts) CollectCallIdentifiers(s.Code, referencedFromBundle);
foreach (var a in t.Attributes)
{
CollectCallIdentifiers(a.Value, referencedFromBundle);
CollectCallIdentifiers(a.DataSourceReference, referencedFromBundle);
}
}
foreach (var m in content.ApiMethods)
{
CollectCallIdentifiers(m.Script, referencedFromBundle);
}
// For each candidate, only report it as a blocker if it looks like a
// resource reference (PascalCase, length > 1) AND it's not present
// anywhere we can satisfy it. We deliberately do not look at language
// keywords or stdlib helpers — the test surface only ever uses
// well-named identifiers.
foreach (var candidate in referencedFromBundle.OrderBy(n => n, StringComparer.Ordinal))
{
if (!LooksLikeResourceName(candidate)) continue;
var isShared = sharedScriptNames.Contains(candidate);
var isExternal = externalSystemNames.Contains(candidate);
if (isShared || isExternal) continue;
blockers.Add(new ImportPreviewItem(
EntityType: "Reference",
Name: candidate,
ExistingVersion: null,
IncomingVersion: null,
Kind: ConflictKind.Blocker,
FieldDiffJson: null,
BlockerReason: $"References SharedScript or ExternalSystem '{candidate}' not present in bundle or target."));
}
return blockers;
}
private static void CollectCallIdentifiers(string? body, HashSet<string> sink)
{
if (string.IsNullOrEmpty(body)) return;
// Find every "Identifier(" or "Identifier." occurrence. The boundary
// before the identifier must NOT be an identifier char so we don't
// match the trailing portion of a longer token.
for (var i = 0; i < body.Length; i++)
{
if (!IsIdentifierStart(body[i])) continue;
if (i > 0 && IsIdentifierChar(body[i - 1])) continue;
var start = i;
while (i < body.Length && IsIdentifierChar(body[i])) i++;
if (i >= body.Length) break;
var trailing = body[i];
if (trailing == '(' || trailing == '.')
{
sink.Add(body[start..i]);
}
}
}
private static bool LooksLikeResourceName(string name)
{
if (name.Length < 2) return false;
if (!char.IsUpper(name[0])) return false;
for (var i = 1; i < name.Length; i++)
{
if (!IsIdentifierChar(name[i])) return false;
}
return true;
}
private static bool IsIdentifierStart(char c) => c == '_' || char.IsLetter(c);
private static bool IsIdentifierChar(char c) => c == '_' || char.IsLetterOrDigit(c);
public Task<ImportResult> ApplyAsync(
Guid sessionId,
IReadOnlyList<ImportResolution> resolutions,
string user,
CancellationToken ct = default)
{
// Filled in by T17.
throw new NotImplementedException("ApplyAsync is implemented by task T17.");
}
}